Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_epoch4

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
512771c
·
verified ·
1 Parent(s): 1443711

Training in progress, epoch 2

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +50 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4a28e73914e045cae017a499a42d5f13c8fb46b6da07937903a4e2d2c9af796
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e68d997793febb5c1418c2527adfac086d861d3ad5baa340d20474b2bf777be
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a829cfb5ff633b6f5d2d82b0b41400958e470d9658a11318df74cc1aa9b07bfa
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4827cd691ede4136d3efc496aea6a85016ead1033c4f5748f9b7495a25c698f2
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84edd0996112fc343f91ff64ad4869c662b156b11862493fcfc21f93a0bff35
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbbec7d672a39900c4c2a6770dd73d0c4d87526fca138082e0d62f35818c7845
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -99,3 +99,53 @@
99
  {"current_steps": 980, "total_steps": 1972, "loss": 0.4823, "lr": 5e-06, "epoch": 1.9853164556962026, "percentage": 49.7, "elapsed_time": "7:44:18", "remaining_time": "7:49:59"}
100
  {"current_steps": 987, "total_steps": 1972, "eval_loss": 0.13791824877262115, "epoch": 1.999493670886076, "percentage": 50.05, "elapsed_time": "7:51:45", "remaining_time": "7:50:48"}
101
  {"current_steps": 990, "total_steps": 1972, "loss": 0.4515, "lr": 5e-06, "epoch": 2.0060759493670886, "percentage": 50.2, "elapsed_time": "7:54:03", "remaining_time": "7:50:13"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  {"current_steps": 980, "total_steps": 1972, "loss": 0.4823, "lr": 5e-06, "epoch": 1.9853164556962026, "percentage": 49.7, "elapsed_time": "7:44:18", "remaining_time": "7:49:59"}
100
  {"current_steps": 987, "total_steps": 1972, "eval_loss": 0.13791824877262115, "epoch": 1.999493670886076, "percentage": 50.05, "elapsed_time": "7:51:45", "remaining_time": "7:50:48"}
101
  {"current_steps": 990, "total_steps": 1972, "loss": 0.4515, "lr": 5e-06, "epoch": 2.0060759493670886, "percentage": 50.2, "elapsed_time": "7:54:03", "remaining_time": "7:50:13"}
102
+ {"current_steps": 1000, "total_steps": 1972, "loss": 0.3891, "lr": 5e-06, "epoch": 2.0263291139240507, "percentage": 50.71, "elapsed_time": "7:58:44", "remaining_time": "7:45:20"}
103
+ {"current_steps": 1010, "total_steps": 1972, "loss": 0.3814, "lr": 5e-06, "epoch": 2.046582278481013, "percentage": 51.22, "elapsed_time": "8:03:25", "remaining_time": "7:40:27"}
104
+ {"current_steps": 1020, "total_steps": 1972, "loss": 0.3794, "lr": 5e-06, "epoch": 2.0668354430379745, "percentage": 51.72, "elapsed_time": "8:08:07", "remaining_time": "7:35:35"}
105
+ {"current_steps": 1030, "total_steps": 1972, "loss": 0.3793, "lr": 5e-06, "epoch": 2.0870886075949366, "percentage": 52.23, "elapsed_time": "8:12:49", "remaining_time": "7:30:43"}
106
+ {"current_steps": 1040, "total_steps": 1972, "loss": 0.3758, "lr": 5e-06, "epoch": 2.1073417721518988, "percentage": 52.74, "elapsed_time": "8:17:31", "remaining_time": "7:25:51"}
107
+ {"current_steps": 1050, "total_steps": 1972, "loss": 0.3868, "lr": 5e-06, "epoch": 2.127594936708861, "percentage": 53.25, "elapsed_time": "8:22:12", "remaining_time": "7:20:59"}
108
+ {"current_steps": 1060, "total_steps": 1972, "loss": 0.3827, "lr": 5e-06, "epoch": 2.1478481012658226, "percentage": 53.75, "elapsed_time": "8:26:54", "remaining_time": "7:16:07"}
109
+ {"current_steps": 1070, "total_steps": 1972, "loss": 0.3852, "lr": 5e-06, "epoch": 2.1681012658227847, "percentage": 54.26, "elapsed_time": "8:31:36", "remaining_time": "7:11:16"}
110
+ {"current_steps": 1080, "total_steps": 1972, "loss": 0.3841, "lr": 5e-06, "epoch": 2.188354430379747, "percentage": 54.77, "elapsed_time": "8:36:17", "remaining_time": "7:06:25"}
111
+ {"current_steps": 1090, "total_steps": 1972, "loss": 0.3818, "lr": 5e-06, "epoch": 2.208607594936709, "percentage": 55.27, "elapsed_time": "8:40:59", "remaining_time": "7:01:34"}
112
+ {"current_steps": 1100, "total_steps": 1972, "loss": 0.3909, "lr": 5e-06, "epoch": 2.2288607594936707, "percentage": 55.78, "elapsed_time": "8:45:40", "remaining_time": "6:56:43"}
113
+ {"current_steps": 1110, "total_steps": 1972, "loss": 0.3884, "lr": 5e-06, "epoch": 2.249113924050633, "percentage": 56.29, "elapsed_time": "8:50:22", "remaining_time": "6:51:52"}
114
+ {"current_steps": 1120, "total_steps": 1972, "loss": 0.387, "lr": 5e-06, "epoch": 2.269367088607595, "percentage": 56.8, "elapsed_time": "8:55:03", "remaining_time": "6:47:01"}
115
+ {"current_steps": 1130, "total_steps": 1972, "loss": 0.3894, "lr": 5e-06, "epoch": 2.289620253164557, "percentage": 57.3, "elapsed_time": "8:59:45", "remaining_time": "6:42:11"}
116
+ {"current_steps": 1140, "total_steps": 1972, "loss": 0.3842, "lr": 5e-06, "epoch": 2.309873417721519, "percentage": 57.81, "elapsed_time": "9:04:26", "remaining_time": "6:37:20"}
117
+ {"current_steps": 1150, "total_steps": 1972, "loss": 0.3908, "lr": 5e-06, "epoch": 2.330126582278481, "percentage": 58.32, "elapsed_time": "9:09:07", "remaining_time": "6:32:30"}
118
+ {"current_steps": 1160, "total_steps": 1972, "loss": 0.3903, "lr": 5e-06, "epoch": 2.350379746835443, "percentage": 58.82, "elapsed_time": "9:13:49", "remaining_time": "6:27:40"}
119
+ {"current_steps": 1170, "total_steps": 1972, "loss": 0.3915, "lr": 5e-06, "epoch": 2.370632911392405, "percentage": 59.33, "elapsed_time": "9:18:31", "remaining_time": "6:22:50"}
120
+ {"current_steps": 1180, "total_steps": 1972, "loss": 0.3924, "lr": 5e-06, "epoch": 2.390886075949367, "percentage": 59.84, "elapsed_time": "9:23:12", "remaining_time": "6:18:00"}
121
+ {"current_steps": 1190, "total_steps": 1972, "loss": 0.3905, "lr": 5e-06, "epoch": 2.411139240506329, "percentage": 60.34, "elapsed_time": "9:27:53", "remaining_time": "6:13:11"}
122
+ {"current_steps": 1200, "total_steps": 1972, "loss": 0.3899, "lr": 5e-06, "epoch": 2.431392405063291, "percentage": 60.85, "elapsed_time": "9:32:35", "remaining_time": "6:08:21"}
123
+ {"current_steps": 1210, "total_steps": 1972, "loss": 0.3878, "lr": 5e-06, "epoch": 2.4516455696202533, "percentage": 61.36, "elapsed_time": "9:37:16", "remaining_time": "6:03:32"}
124
+ {"current_steps": 1220, "total_steps": 1972, "loss": 0.3907, "lr": 5e-06, "epoch": 2.4718987341772154, "percentage": 61.87, "elapsed_time": "9:41:58", "remaining_time": "5:58:43"}
125
+ {"current_steps": 1230, "total_steps": 1972, "loss": 0.3937, "lr": 5e-06, "epoch": 2.492151898734177, "percentage": 62.37, "elapsed_time": "9:46:39", "remaining_time": "5:53:54"}
126
+ {"current_steps": 1240, "total_steps": 1972, "loss": 0.393, "lr": 5e-06, "epoch": 2.512405063291139, "percentage": 62.88, "elapsed_time": "9:51:21", "remaining_time": "5:49:05"}
127
+ {"current_steps": 1250, "total_steps": 1972, "loss": 0.3921, "lr": 5e-06, "epoch": 2.5326582278481014, "percentage": 63.39, "elapsed_time": "9:56:02", "remaining_time": "5:44:16"}
128
+ {"current_steps": 1260, "total_steps": 1972, "loss": 0.386, "lr": 5e-06, "epoch": 2.552911392405063, "percentage": 63.89, "elapsed_time": "10:00:44", "remaining_time": "5:39:27"}
129
+ {"current_steps": 1270, "total_steps": 1972, "loss": 0.3929, "lr": 5e-06, "epoch": 2.573164556962025, "percentage": 64.4, "elapsed_time": "10:05:26", "remaining_time": "5:34:39"}
130
+ {"current_steps": 1280, "total_steps": 1972, "loss": 0.3956, "lr": 5e-06, "epoch": 2.5934177215189873, "percentage": 64.91, "elapsed_time": "10:10:07", "remaining_time": "5:29:51"}
131
+ {"current_steps": 1290, "total_steps": 1972, "loss": 0.3985, "lr": 5e-06, "epoch": 2.6136708860759494, "percentage": 65.42, "elapsed_time": "10:14:49", "remaining_time": "5:25:02"}
132
+ {"current_steps": 1300, "total_steps": 1972, "loss": 0.3949, "lr": 5e-06, "epoch": 2.6339240506329116, "percentage": 65.92, "elapsed_time": "10:19:31", "remaining_time": "5:20:14"}
133
+ {"current_steps": 1310, "total_steps": 1972, "loss": 0.3949, "lr": 5e-06, "epoch": 2.6541772151898733, "percentage": 66.43, "elapsed_time": "10:24:12", "remaining_time": "5:15:26"}
134
+ {"current_steps": 1320, "total_steps": 1972, "loss": 0.3972, "lr": 5e-06, "epoch": 2.6744303797468354, "percentage": 66.94, "elapsed_time": "10:28:54", "remaining_time": "5:10:38"}
135
+ {"current_steps": 1330, "total_steps": 1972, "loss": 0.3975, "lr": 5e-06, "epoch": 2.6946835443037975, "percentage": 67.44, "elapsed_time": "10:33:36", "remaining_time": "5:05:50"}
136
+ {"current_steps": 1340, "total_steps": 1972, "loss": 0.3998, "lr": 5e-06, "epoch": 2.714936708860759, "percentage": 67.95, "elapsed_time": "10:38:17", "remaining_time": "5:01:02"}
137
+ {"current_steps": 1350, "total_steps": 1972, "loss": 0.3972, "lr": 5e-06, "epoch": 2.7351898734177214, "percentage": 68.46, "elapsed_time": "10:42:58", "remaining_time": "4:56:14"}
138
+ {"current_steps": 1360, "total_steps": 1972, "loss": 0.3932, "lr": 5e-06, "epoch": 2.7554430379746835, "percentage": 68.97, "elapsed_time": "10:47:40", "remaining_time": "4:51:27"}
139
+ {"current_steps": 1370, "total_steps": 1972, "loss": 0.3999, "lr": 5e-06, "epoch": 2.7756962025316456, "percentage": 69.47, "elapsed_time": "10:52:22", "remaining_time": "4:46:39"}
140
+ {"current_steps": 1380, "total_steps": 1972, "loss": 0.3974, "lr": 5e-06, "epoch": 2.7959493670886078, "percentage": 69.98, "elapsed_time": "10:57:03", "remaining_time": "4:41:52"}
141
+ {"current_steps": 1390, "total_steps": 1972, "loss": 0.4004, "lr": 5e-06, "epoch": 2.81620253164557, "percentage": 70.49, "elapsed_time": "11:01:44", "remaining_time": "4:37:04"}
142
+ {"current_steps": 1400, "total_steps": 1972, "loss": 0.3945, "lr": 5e-06, "epoch": 2.8364556962025316, "percentage": 70.99, "elapsed_time": "11:06:26", "remaining_time": "4:32:17"}
143
+ {"current_steps": 1410, "total_steps": 1972, "loss": 0.4014, "lr": 5e-06, "epoch": 2.8567088607594937, "percentage": 71.5, "elapsed_time": "11:11:07", "remaining_time": "4:27:30"}
144
+ {"current_steps": 1420, "total_steps": 1972, "loss": 0.3987, "lr": 5e-06, "epoch": 2.876962025316456, "percentage": 72.01, "elapsed_time": "11:15:49", "remaining_time": "4:22:42"}
145
+ {"current_steps": 1430, "total_steps": 1972, "loss": 0.3983, "lr": 5e-06, "epoch": 2.8972151898734175, "percentage": 72.52, "elapsed_time": "11:20:30", "remaining_time": "4:17:55"}
146
+ {"current_steps": 1440, "total_steps": 1972, "loss": 0.4016, "lr": 5e-06, "epoch": 2.9174683544303797, "percentage": 73.02, "elapsed_time": "11:25:11", "remaining_time": "4:13:08"}
147
+ {"current_steps": 1450, "total_steps": 1972, "loss": 0.4105, "lr": 5e-06, "epoch": 2.937721518987342, "percentage": 73.53, "elapsed_time": "11:29:53", "remaining_time": "4:08:21"}
148
+ {"current_steps": 1460, "total_steps": 1972, "loss": 0.3992, "lr": 5e-06, "epoch": 2.957974683544304, "percentage": 74.04, "elapsed_time": "11:34:34", "remaining_time": "4:03:34"}
149
+ {"current_steps": 1470, "total_steps": 1972, "loss": 0.403, "lr": 5e-06, "epoch": 2.978227848101266, "percentage": 74.54, "elapsed_time": "11:39:15", "remaining_time": "3:58:47"}
150
+ {"current_steps": 1480, "total_steps": 1972, "loss": 0.4008, "lr": 5e-06, "epoch": 2.9984810126582278, "percentage": 75.05, "elapsed_time": "11:43:56", "remaining_time": "3:54:00"}
151
+ {"current_steps": 1480, "total_steps": 1972, "eval_loss": 0.1451626569032669, "epoch": 2.9984810126582278, "percentage": 75.05, "elapsed_time": "11:48:23", "remaining_time": "3:55:29"}